| ID |
CVE-2025-49847
|
| Sažetak |
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662. |
| Reference |
|
| CVSS |
| Base: | 8.8 |
| Impact: | 5.9 |
| Exploitability: | 2.8 |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| NETWORK |
LOW |
NONE |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| HIGH |
HIGH |
HIGH |
|
| CVSS vektor |
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| Zadnje važnije ažuriranje |
17-06-2025 - 20:50 |
| Objavljeno |
17-06-2025 - 20:15 |
